{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T16:54:10Z","timestamp":1759683250550,"version":"3.37.3"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,5,11]],"date-time":"2018-05-11T00:00:00Z","timestamp":1525996800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,5,11]],"date-time":"2018-05-11T00:00:00Z","timestamp":1525996800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP150103071","DP150102728"],"award-info":[{"award-number":["DP150103071","DP150102728"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DE140100679","DP170103710"],"award-info":[{"award-number":["DE140100679","DP170103710"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC61232006"],"award-info":[{"award-number":["NSFC61232006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP170101628"],"award-info":[{"award-number":["DP170101628"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1007\/s00778-018-0505-x","type":"journal-article","created":{"date-parts":[[2018,5,11]],"date-time":"2018-05-11T10:40:56Z","timestamp":1526035256000},"page":"471-495","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Efficient set containment join"],"prefix":"10.1007","volume":"27","author":[{"given":"Jianye","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuemin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,11]]},"reference":[{"unstructured":"http:\/\/liu.cs.uic.edu\/download\/data\/","key":"505_CR1"},{"unstructured":"http:\/\/www.cim.mcgill.ca\/~dudek\/206\/Logs\/AOL-user-ct-collection","key":"505_CR2"},{"unstructured":"http:\/\/www.informatik.uni-freiburg.de\/~cziegler\/BX\/","key":"505_CR3"},{"unstructured":"http:\/\/dai-labor.de\/IRML\/datasets","key":"505_CR4"},{"unstructured":"http:\/\/www.discogs.com\/","key":"505_CR5"},{"unstructured":"http:\/\/www.cs.cmu.edu\/~enron","key":"505_CR6"},{"unstructured":"http:\/\/www.dtic.upf.edu\/~ocelma\/MusicRecommendationDataset\/lastfm-1K.html","key":"505_CR7"},{"unstructured":"http:\/\/konect.uni-koblenz.de\/networks\/lkml_person-thread","key":"505_CR8"},{"unstructured":"http:\/\/socialnetworks.mpi-sws.org\/data-imc2007.html","key":"505_CR9"},{"unstructured":"http:\/\/www.clearbits.net\/torrents\/1881-dec-2011","key":"505_CR10"},{"unstructured":"http:\/\/vi.sualize.us\/","key":"505_CR11"},{"unstructured":"http:\/\/wiki.dbpedia.org\/Downloads","key":"505_CR12"},{"doi-asserted-by":"crossref","unstructured":"Afrati, F.N., Sarma, A.D., Menestrina, D., Parameswaran, A., Ullman, J.D.: Fuzzy joins using mapreduce. In: ICDE, pp. 498\u2013509 (2012)","key":"505_CR13","DOI":"10.1109\/ICDE.2012.66"},{"doi-asserted-by":"crossref","unstructured":"Agrawal, P., Arasu, A., Kaushik, R.: On indexing error-tolerant set containment. In: SIGMOD, pp. 927\u2013938 (2010)","key":"505_CR14","DOI":"10.1145\/1807167.1807267"},{"unstructured":"Arasu, A., Ganti, V., Kaushik, R.: Efficient exact set-similarity joins. In: VLDB, pp. 918\u2013929 (2006)","key":"505_CR15"},{"doi-asserted-by":"crossref","unstructured":"Baeza-Yates, R., Salinger, A.: A fast set intersection algorithm for sorted sequences. In: CPM (2004)","key":"505_CR16","DOI":"10.1007\/978-3-540-27801-6_30"},{"doi-asserted-by":"crossref","unstructured":"Bayardo, R.J., Ma, Y., Srikant, R.: Scaling up all pairs similarity search. In: WWW, pp. 131\u2013140 (2007)","key":"505_CR17","DOI":"10.1145\/1242572.1242591"},{"doi-asserted-by":"crossref","unstructured":"Bouros, P., Mamoulis, N., Ge, S., Terrovitis, M.: Set containment join revisited. In: Knowledge and Information Systems, pp. 1\u201328 (2015)","key":"505_CR18","DOI":"10.1007\/s10115-015-0895-7"},{"doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganti, V., Kaushik, R.: A primitive operator for similarity joins in data cleaning. In: ICDE (2006)","key":"505_CR19","DOI":"10.1109\/ICDE.2006.9"},{"doi-asserted-by":"crossref","unstructured":"Deng, D., Li, G., Hao, S., Wang, J., Feng, J.: Massjoin: a mapreduce-based method for scalable string similarity joins. In: ICDE, pp. 340\u2013351 (2014)","key":"505_CR20","DOI":"10.1109\/ICDE.2014.6816663"},{"doi-asserted-by":"crossref","unstructured":"Deng, D., Li, G., Wen, H., Feng, J.: An efficient partition based method for exact set similarity joins. In: VLDB, pp. 360\u2013371 (2015)","key":"505_CR21","DOI":"10.14778\/2856318.2856330"},{"doi-asserted-by":"crossref","unstructured":"Han, J., Pei, J., Yin, Y.: Mining frequent patterns without candidate generation. In: SIGMOD, pp. 1\u201312 (2000)","key":"505_CR22","DOI":"10.1145\/335191.335372"},{"unstructured":"Helmer, S., Moerkotte, G.: Evaluation of main memory join algorithms for joins with set comparison predicates. In: VLDB, pp. 386\u2013395 (1997)","key":"505_CR23"},{"doi-asserted-by":"crossref","unstructured":"Hmedeh, Z., Kourdounakis, H., Christophides, V., Du Mouza, C., Scholl, M., Travers., N.: Subscription indexes for web syndication systems. In: EDBT, pp. 312\u2013323 (2012)","key":"505_CR24","DOI":"10.1145\/2247596.2247634"},{"doi-asserted-by":"crossref","unstructured":"Hu, X., Tao, Y., Yi, K.: Output-optimal parallel algorithms for similarity joins. In: PODS, pp. 79\u201390 (2017)","key":"505_CR25","DOI":"10.1145\/3034786.3056110"},{"doi-asserted-by":"crossref","unstructured":"Jampani, R., Pudi, V.: Using prefix-trees for efficiently computing set joins. In: DASFAA, pp. 761\u2013772 (2005)","key":"505_CR26","DOI":"10.1007\/11408079_69"},{"doi-asserted-by":"crossref","unstructured":"Kunkel, A., Rheinl\u00e4nder, A., Schiefer, C., Helmer, S., Bouros, P., Leser, U.: Piejoin: towards parallel set containment joins. In: SSDBM, p. 11 (2016)","key":"505_CR27","DOI":"10.1145\/2949689.2949694"},{"doi-asserted-by":"crossref","unstructured":"Leskovec, J., Backstrom, L., Kleinberg, J.: Meme-tracking and the dynamics of the news cycle. In: SIGKDD, pp. 497\u2013506 (2009)","key":"505_CR28","DOI":"10.1145\/1557019.1557077"},{"doi-asserted-by":"crossref","unstructured":"Li, C., Lu, J., Lu, Y.: Efficient merging and filtering algorithms for approximate string searches. In: ICDE, pp. 257\u2013266 (2008)","key":"505_CR29","DOI":"10.1109\/ICDE.2008.4497434"},{"doi-asserted-by":"crossref","unstructured":"Luo, Y., Fletcher, G.H., Hidders, J., De Bra, P.: Efficient and scalable trie-based algorithms for computing set containment relations. In: ICDE, pp. 303\u2013314 (2015)","key":"505_CR30","DOI":"10.1109\/ICDE.2015.7113293"},{"doi-asserted-by":"crossref","unstructured":"Mamoulis, N.: Efficient processing of joins on set-valued attributes. In: SIGMOD, pp. 157\u2013168 (2003)","key":"505_CR31","DOI":"10.1145\/872757.872778"},{"doi-asserted-by":"crossref","unstructured":"Mann, W., Augsten, N., Bouros, P.: An empirical evaluation of set similarity join techniques. In: VLDB, pp. 636\u2013647 (2016)","key":"505_CR32","DOI":"10.14778\/2947618.2947620"},{"doi-asserted-by":"crossref","unstructured":"Melnik, S., Garcia-Molina, H.: Divide-and-conquer algorithm for computing set containment joins. In: EDBT, pp. 427\u2013444 (2002)","key":"505_CR33","DOI":"10.1007\/3-540-45876-X_28"},{"issue":"1","key":"505_CR34","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/762471.762474","volume":"28","author":"S Melnik","year":"2003","unstructured":"Melnik, S., Garcia Molina, H.: Adaptive algorithms for set containment joins. TODS 28(1), 56\u201399 (2003)","journal-title":"TODS"},{"doi-asserted-by":"crossref","unstructured":"Metwally, A., Faloutsos, C.: V-smart-join: a scalable mapreduce framework for all-pair similarity joins of multisets and vectors. In: VLDB, pp. 704\u2013715 (2012)","key":"505_CR35","DOI":"10.14778\/2212351.2212353"},{"unstructured":"Ramasamy, K., Patel, J.M., Naughton, J.F., Kaushik, R.: Set containment joins: the good, the bad and the ugly. In: VLDB, pp. 351\u2013362 (2000)","key":"505_CR36"},{"doi-asserted-by":"crossref","unstructured":"Sun, J., Shang, Z., Li, G., Dend, D., Bao, Z.: Dima: a distributed in-memory similarity-based query processing system. In: VLDB, pp. 1925\u20131928 (2017)","key":"505_CR37","DOI":"10.14778\/3137765.3137810"},{"doi-asserted-by":"crossref","unstructured":"Terrovitis, M., Bouros, P., Vassiliadis, P., Sellis, T., Mamoulis, N.: Efficient answering of set containment queries for skewed item distributions. In: EDBT, pp. 225\u2013236 (2011)","key":"505_CR38","DOI":"10.1145\/1951365.1951394"},{"doi-asserted-by":"crossref","unstructured":"Terrovitis, M., Passas, S., Vassiliadis, P., Sellis, T.: A combination of trie-trees and inverted files for the indexing of set-valued attributes. In: CIKM, pp. 728\u2013737 (2006)","key":"505_CR39","DOI":"10.1145\/1183614.1183718"},{"doi-asserted-by":"crossref","unstructured":"Vernica, R., Carey, M.J., Li, C.: Efficient parallel set-similarity joins using mapreduce. In: SIGMOD, pp. 495\u2013506 (2010)","key":"505_CR40","DOI":"10.1145\/1807167.1807222"},{"doi-asserted-by":"crossref","unstructured":"Wang, J., Feng, J., Li, G.: Trie-join: Efficient trie-based string similarity joins with edit-distance constraints. In: VLDB, pp. 1219\u20131230 (2010)","key":"505_CR41","DOI":"10.14778\/1920841.1920992"},{"doi-asserted-by":"crossref","unstructured":"Wang, J., Li, G., Feng, J.: Can we beat the prefix filtering? An adaptive framework for similarity join and search. In: SIGMOD, pp. 85\u201396 (2012)","key":"505_CR42","DOI":"10.1145\/2213836.2213847"},{"doi-asserted-by":"crossref","unstructured":"Wang, X., Qin, L., Lin, X., Zhang, Y., Chang, L.: Leveraging set relations in exact set similarity join. In: VLDB, pp. 925\u2013936 (2017)","key":"505_CR43","DOI":"10.14778\/3099622.3099624"},{"doi-asserted-by":"crossref","unstructured":"Xiao, C., Wang, W., Lin, X., Shang, H.: Top-k set similarity joins. In: ICDE, pp. 916\u2013927 (2009)","key":"505_CR44","DOI":"10.1109\/ICDE.2009.111"},{"doi-asserted-by":"crossref","unstructured":"Xiao, C., Wang, W., Lin, X., Yu, J.X.: Efficient similarity joins for near duplicate detection. In: WWW, pp. 131\u2013140 (2008)","key":"505_CR45","DOI":"10.1145\/1367497.1367516"},{"issue":"2","key":"505_CR46","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1145\/176567.176573","volume":"19","author":"TW Yan","year":"1994","unstructured":"Yan, T.W., Garc\u00eda-Molina, H.: Index structures for selective dissemination of information under the boolean model. TODS 19(2), 332\u2013364 (1994)","journal-title":"TODS"},{"doi-asserted-by":"crossref","unstructured":"Zhu, E., Nargesian, F., Pu, K.Q., Miller, R.J.: LSH ensemble: Internet scale domain search. In: VLDB, pp. 1185\u20131196 (2016)","key":"505_CR47","DOI":"10.14778\/2994509.2994534"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-018-0505-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-018-0505-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-018-0505-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,16]],"date-time":"2020-05-16T15:33:16Z","timestamp":1589643196000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-018-0505-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,11]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,8]]}},"alternative-id":["505"],"URL":"https:\/\/doi.org\/10.1007\/s00778-018-0505-x","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"type":"print","value":"1066-8888"},{"type":"electronic","value":"0949-877X"}],"subject":[],"published":{"date-parts":[[2018,5,11]]},"assertion":[{"value":"21 May 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}